Open-sourcing MuJoCo

In October 2021, we introduced that we acquired the MuJoCo physics simulatorand made it freely out there for everybody to assist analysis in all places. We additionally dedicated to creating and sustaining MuJoCo as a free, open-source, community-driven mission with best-in-class capabilities. At this time, we’re thrilled to report that open sourcing is full and your entire codebase is on GitHub!

Right here, we clarify why MuJoCo is a good platform for open-source collaboration and share a preview of our roadmap going ahead.

A platform for collaboration

Physics simulators are crucial instruments in trendy robotics analysis and infrequently fall into these two classes:

1. Closed-source, business software program.
2. Open-source software program, usually created in academia.

The primary class is opaque to the consumer, and though generally free to make use of, can’t be modified and is difficult to know. The second class usually has a smaller consumer base and suffers when its builders and maintainers graduate.

MuJoCo is without doubt one of the few full-featured simulators backed by a longtime firm, which is actually open supply. As a research-driven organisation, we view MuJoCo as a platform for collaboration, the place roboticists and engineers can be a part of us to develop one of many world’s greatest robotic simulators.

Options that make MuJoCo notably engaging for collaboration are:

• Full-featured simulator that may model complex mechanisms.
• Readable, performant, transportable code.
• Simply extensible codebase.
• Detailed documentation: each user-facing and code feedback.

We hope that colleagues throughout academia and the OSS neighborhood profit from this platform and contribute to the codebase, bettering analysis for everybody.

Efficiency

As a C library with no dynamic reminiscence allocation, MuJoCo could be very quick. Sadly, uncooked physics velocity has traditionally been hindered by Python wrappers, which made batched, multi-threaded operations non-performant because of the presence of the International Interpreter Lock (GIL) and non-compiled code. In our roadmap beneath, we handle this situation going ahead.

For now, we’d wish to share some benchmarking outcomes for 2 frequent fashions. The outcomes have been obtained on a normal AMD Ryzen 9 5950X machine, working Home windows 10.

Roadmap

Right here’s our near-term roadmap for MuJoCo:

• Unlock MuJoCo’s velocity potential with batched, multi-threaded simulation.
• Assist bigger scenes with enhancements to inside reminiscence administration.
• New incremental compiler with higher mannequin composability.
• Assist for higher rendering through Unity integration.
• Native assist for physics derivatives, each analytical and finite-differenced.

Study extra

Useful assets about MuJoCo:

We stay up for receiving your contributions!